cell-AAP

Utilities for the semi-automated generation of instance segmentation annotations to be used for neural network training. Utilities are built ontop of UMAP, HDBSCAN and a finetuned encoder version of FAIR's Segment Anything Model developed by Computational Cell Analytics for the project micro-sam. In addition to providing utilies for annotation building, we train networks using FAIR's detectron2 to

1. Demonstrate the efficacy of our utilities.
2. Be used for microscopy annotation of supported cell lines

Cell-line specific models currently include:

1. HeLa
2. U2OS

Models have demonstrated performance efficacy on:

1. HT1080 (HeLa model)
2. RPE1 (U2OS model)

We've also developed a napari application for the usage of these pre-trained networks.

We highly recommend installing cell-AAP in a clean conda environment. To do so you must have miniconda or anaconda installed.

If a conda distribution has been installed:

1. Create and activate a clean environment

    conda create -n cell-aap-env python=3.11.0
    conda activate cell-app-env

2. Within this environment install pip

    conda install pip

3. Then install cell-AAP from PyPi

    pip install cell-AAP --upgrade

4. Finally detectron2 must be built from source, atop cell-AAP

    #For MacOS
    CC=clang CXX=clang++ ARCHFLAGS="-arch arm64" python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
   
    #For other operating systems 
    python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'

1. To open napari simply type "napari" into the command line, ensure that you are working the correct environment
2. To instantiate the plugin navigate to the "Plugins" menu and select "cell-AAP"
3. You should now see the Plugin, where you can select an image, display it, and run inference on it.

If running inference on large volumes of data, i.e. timeseries data >= 300 MB in size, we recommend to proceed in the following manner.

1. Assemble a small, < 100 MB, substack of your data using python or a program like ImageJ
2. Use this substack to find the optimal parameters for your data, (Number of Cells, Network confidence threshold)
3. Run Inference over the volume using the discovered optimal parameters

Once inference is complete the following colors indicate class prediction

• Red: Non-mitotic
• Blue: Mitotic

For analysis purposes, masks in the semantic and instance segmentations have the following value mapping: Semantic

• 1: Non-mitotic
• 100: Mitotic

Instance

• $2x$: Non-mitotic
• $2x-1$: Mitotic